README.md

metadata

quantized_by: bartowski

Exllama v2 Quantizations of TinyLlama-1.1B-Chat-v1.0 at 8.0 bits per weight

Using turboderp's ExLlamaV2 v0.0.11 for quantization.

Conversion was done using the default calibration dataset.

Original model: https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0

Download instructions

With git:

git clone --single-branch --branch 8.0 https://huggingface.co/bartowski/TinyLlama-1.1B-Chat-v1.0-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

To download from a different branch, add the --revision parameter:

mkdir TinyLlama-1.1B-Chat-v1.0-exl2
huggingface-cli download bartowski/TinyLlama-1.1B-Chat-v1.0-exl2 --revision 8_0 --local-dir TinyLlama-1.1B-Chat-v1.0-exl2 --local-dir-use-symlinks False